A power system transient stability assessment method based on active learning

Abstract Due to the wide deployment of phasor measurement unit, the real‐time assessment of transient stability based on machine learning shows great potential for development. In order to solve the problem of time‐consuming data generation of offline training in such methods and the difficulty of q...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuqiong Zhang, Qiang Zhao, Bendong Tan, Jun Yang
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	active learning phasor measurement unit transient stability assessment Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/c6390839e33541c1a335c90d35bfc3a4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c6390839e33541c1a335c90d35bfc3a4
record_format	dspace
spelling	oai:doaj.org-article:c6390839e33541c1a335c90d35bfc3a42021-11-19T06:50:34ZA power system transient stability assessment method based on active learning2051-330510.1049/tje2.12068https://doaj.org/article/c6390839e33541c1a335c90d35bfc3a42021-11-01T00:00:00Zhttps://doi.org/10.1049/tje2.12068https://doaj.org/toc/2051-3305Abstract Due to the wide deployment of phasor measurement unit, the real‐time assessment of transient stability based on machine learning shows great potential for development. In order to solve the problem of time‐consuming data generation of offline training in such methods and the difficulty of quickly updating the model after the grid changes, the paper proposes a method for transient stability assessment (TSA) of power systems based on active learning. Firstly, different operation conditions and different faults are considered to perform short‐time simulation (simulation to the instant of fault clearance) to generate unlabelled samples. After the careful selection of critical TSA features, a part of samples are randomly selected for long‐term simulation to label the transient status of these samples, and random forest is further trained to construct TSA model. Finally some data is selected in the remaining unlabelled samples with higher information entropy to label and retrain the model until the model accuracy no longer changes. The simulation on the test power system shows that the method proposed in this paper can effectively reduce the time of offline simulation, and greatly improve the efficiency of model, and is also robust to wide‐area noise.Yuqiong ZhangQiang ZhaoBendong TanJun YangWileyarticleactive learningphasor measurement unittransient stability assessmentEngineering (General). Civil engineering (General)TA1-2040ENThe Journal of Engineering, Vol 2021, Iss 11, Pp 715-723 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	active learning phasor measurement unit transient stability assessment Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	active learning phasor measurement unit transient stability assessment Engineering (General). Civil engineering (General) TA1-2040 Yuqiong Zhang Qiang Zhao Bendong Tan Jun Yang A power system transient stability assessment method based on active learning
description	Abstract Due to the wide deployment of phasor measurement unit, the real‐time assessment of transient stability based on machine learning shows great potential for development. In order to solve the problem of time‐consuming data generation of offline training in such methods and the difficulty of quickly updating the model after the grid changes, the paper proposes a method for transient stability assessment (TSA) of power systems based on active learning. Firstly, different operation conditions and different faults are considered to perform short‐time simulation (simulation to the instant of fault clearance) to generate unlabelled samples. After the careful selection of critical TSA features, a part of samples are randomly selected for long‐term simulation to label the transient status of these samples, and random forest is further trained to construct TSA model. Finally some data is selected in the remaining unlabelled samples with higher information entropy to label and retrain the model until the model accuracy no longer changes. The simulation on the test power system shows that the method proposed in this paper can effectively reduce the time of offline simulation, and greatly improve the efficiency of model, and is also robust to wide‐area noise.
format	article
author	Yuqiong Zhang Qiang Zhao Bendong Tan Jun Yang
author_facet	Yuqiong Zhang Qiang Zhao Bendong Tan Jun Yang
author_sort	Yuqiong Zhang
title	A power system transient stability assessment method based on active learning
title_short	A power system transient stability assessment method based on active learning
title_full	A power system transient stability assessment method based on active learning
title_fullStr	A power system transient stability assessment method based on active learning
title_full_unstemmed	A power system transient stability assessment method based on active learning
title_sort	power system transient stability assessment method based on active learning
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/c6390839e33541c1a335c90d35bfc3a4
work_keys_str_mv	AT yuqiongzhang apowersystemtransientstabilityassessmentmethodbasedonactivelearning AT qiangzhao apowersystemtransientstabilityassessmentmethodbasedonactivelearning AT bendongtan apowersystemtransientstabilityassessmentmethodbasedonactivelearning AT junyang apowersystemtransientstabilityassessmentmethodbasedonactivelearning AT yuqiongzhang powersystemtransientstabilityassessmentmethodbasedonactivelearning AT qiangzhao powersystemtransientstabilityassessmentmethodbasedonactivelearning AT bendongtan powersystemtransientstabilityassessmentmethodbasedonactivelearning AT junyang powersystemtransientstabilityassessmentmethodbasedonactivelearning
_version_	1718420339852050432

A power system transient stability assessment method based on active learning

Ejemplares similares